吉林大学学报(信息科学版) ›› 2019, Vol. 37 ›› Issue (3): 260-264.

• • 上一篇    下一篇

基于互信息的变模态分解算法及应用

尹淑欣1,2,段玉波1,刘云菲1   

  1. 1. 东北石油大学电气信息工程学院,黑龙江大庆163318; 2. 黑龙江八一农垦大学电气与信息学院,黑龙江大庆163319
  • 收稿日期:2018-09-02 出版日期:2019-05-20 发布日期:2019-06-21
  • 通讯作者: 段玉波( 1951— ) ,东北石油大学教授,博士生导师,主要从事智能信号处理、管道泄漏点检测研究,( Tel) 86-13904697561( E-mail) eienepu@163. com。 E-mail:eienepu@163. com
  • 作者简介:尹淑欣( 1977— ) ,女,黑龙江五常人,东北石油大学博士研究生,黑龙江八一农垦大学讲师,主要从事油气信息与控制、激光光电检测等研究,( Tel) 86-13836904969( E-mail) byau_ysx@163. com; 通讯作者: 段玉波( 1951— ) ,东北石油大学教授,博士生导师,主要从事智能信号处理、管道泄漏点检测研究,( Tel) 86-13904697561( E-mail) eienepu@163. com。
  • 基金资助:
    黑龙江省自然科学基金资助项目( E2016013)

Variational Mode Decomposition Filtering Combining Mutual Information and Its Application#br#

YIN Shuxin1,2,DUAN Yubo1,LIU Yunfei1#br#   

  1. 1. School of Electrical Engineering and Information,Northeast Petroleum University,Daqing 163318,China;
    2. College of Electrical and Information,Heilongjiang Bayi Agricultural University,Daqing 163319,China
  • Received:2018-09-02 Online:2019-05-20 Published:2019-06-21

摘要: 为解决传统变模态分解( VMD: Variable Mode Decomposition) 结合算法中,K 值选择没有标准,从而导致信号提取存在一定程度误差的问题,提出一种基于互信息的变模态分解有效本征模态函数( IMFs: Intrinsic Mode Function) 的判断方法。该算法通过原始信号与VMD 所获得的IMFs 的和之间的差值,实现预置标度K 值的模糊优选提取信号的主要特征。仿真信号实验表明,所提方法具有最大的输出信噪比和最小均方误差( MSE: Mean Square Error) ,实现了K 的模糊优选,并通过实验验证了该方法对管道泄漏信号滤波的有效性。

关键词: 变模态分解, 互信息, 相关系数, 最小均方误差, 管道泄漏检测

Abstract: In traditional VMD ( Variable Mode Decomposition) combination algorithms,there is no standard for the K value selection,which leads to a certain degree of error in signal extraction. In order to solve the problem,
a method for judging the effective IMFs of VMD based on mutual information is introduced. The algorithm
implements fuzzy optimization of the preset scale K value to extract the main features of the signal by the
difference between the original signal and the sum of the IMFs obtained by the VMD. Simulation results show that
the proposed method has the largest output SNR ( Signal-to-Noise Ratio) and minimum MSE ( Mean Square
Error) ,and realizes the fuzzy optimization of K. The effectiveness of the proposed method for filtering pipeline
leakage signals is verified by experiments.

Key words: variable mode decomposition ( VMD) , mutual information, correlation coefficient, mean square error ( MES) , pipeline leak detection

中图分类号: 

  • TP29